KG Memory

KG: Knowledge Graph

Follow this topic Ask about this topic

Latest papers

13 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Toward a Compositional Knowledge Architecture for a Shared Organizational Cortex
Nov 3, 2026Andrew Miracle, Phyl Georgiou, Christine Okoth +1Knowledge Representation KG Memory
Robin Inc. · Nosen
FIRME: Registry-Anchored Memory Graphs for Evolving, Heterogeneous Investor Knowledge
Oct 29, 2026Yunbai Zhang, Yunyi Gao, Han-Tai ShiaoKG Memory Knowledge Graphs
The Vanguard, Malvern, Pennsylvania, USA
Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents
Aug 29, 2026Theo Rusu, Sourena Khanzadeh, Manar AlalfiGraph-Based Agent Memory Long-Term Conversational Memory
Department of Computer Science Toronto Metropolitan University Toronto, Ontario, Canada · The Creative School Toronto Metropolitan University Toronto, Ontario, Canada · Flybits, Creative AI Hub Toronto, Ontario, Canada
A Graph-Native Bitemporal Memory Store for Conversational AI Agents
Jul 29, 2026Alp Niksarli, Gopesh BahetiPersistent Memory for Language Models Temporal KGs
Davidson College
G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agents
Jun 11, 2026Minjun Choi, Yoonjin Jang, Sangwon Youn +1Conversational Memory KG Memory
Sungkyunkwan University, Suwon, Republic of Korea
Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History
Jun 5, 2026Liuyin WangTemporal KGs Long-Context QA
Independent Researcher
TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management
Jun 4, 2026Shweta MishraKG Memory LLM Agent Memory
Independent Researcher, India.
FundaPod: A Multi-Persona Agent Pod Architecture with Knowledge Graph Memory for AI-Assisted Fundamental Investment Research
May 27, 2026Di Zhu, Lei Nico Zheng, Zihan ChenMulti-Agent LLM Systems KG Memory
Stevens Institute of Technology Hoboken, NJ, USA · UMass Boston Boston, MA, USA
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
May 11, 2026Ruiyi Yang, Zechen Li, Hao Xue +2Agent Memory Continual Learning for LLM Agents
University of New South Wales · The Hong Kong University of Science and Technology (Guangzhou) · Mohamed Bin Zayed University of Artificial Intelligence
WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation
Apr 20, 2026Harish Santhanalakshmi GanesanTemporal KGs Entity Resolution
Independent Researcher
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Apr 13, 2026Weixian Waylon Li, Jiaxin Zhang, Xianan Jim Yang +2KG Memory Temporal KGs
University of Edinburgh · LIGHTSPEED · Independent Researcher
ElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agents
Mar 26, 2026Cristian Lupascu, Alexandru LupascuKG Memory LLM Agent Memory
Elephant Broker, 050141 Bucharest, Romania
EchoGuard: An Agentic Framework with Knowledge-Graph Memory for Detecting Manipulative Communication in Longitudinal Dialogue
Mar 5, 2026Ratna Kandala, Niva Manchanda, Akshata Kishore Moharir +1KG Memory Agentic AI
University of Kansas · University of Maryland · University of Florida

Nov 3, 2026J/K move · Enter open · S save

Toward a Compositional Knowledge Architecture for a Shared Organizational Cortex

Andrew Miracle, Phyl Georgiou, Christine Okoth, Ese Monday

Robin Inc. · Nosen

Knowledge Representation KG Memory

Open paper AskPDF arXiv

Organizations accumulate evidence in conversations, documents, decisions and relationships, but they act on interpretations: judgements assembled from several observations, resting on assumptions, and revised as circumstances change. Existing retrieval, knowledge graphs and agent memory keep the records and lose the interpretation. We propose a four-layer architecture, Signals, Domains, Claims and Dimensions, in which interpretations persist with their justifications and standing, a truth-maintenance network revises that standing as evidence changes, and validated, versioned Dimensions position interpretations on named axes. We call the result a shared organizational cortex. In a registered retrieval experiment, the Dimension term gains 0.028 nDCG@10 (p = 0.002). In system-level comparisons, the full retrieval configuration improves nDCG@10 by 0.081 over Signals-only and 0.053 over graph-augmented Signals-only retrieval (both reported p < 0.001). The architecture gives organizations a persistent, revisable basis for shared judgement.